ModelVerdict

Amanda Kim

Englisch (USA)E-Mail9 Felder

Dokument en-p0033 · Layout signature · 9 Felder · öffentlicher Teil des Datensatzes · Dieselbe Rechnung auf Tschechisch → · Fehler in diesem Beispiel melden

E-Mail-Text (das Modell hat genau diesen Text erhalten)

From: Amanda Kim <amanda.kim@mills.example>
To: support@barber.example
Date: Thu, Jan 29, 2026 at 1:20 PM
Subject: Damaged goods

Hello,

The parts you delivered don't match our order, you sent us a different model. This is about our order ORD-2026-3290.

It's invoice 2026-9857. This is completely unacceptable and very frustrating. If this isn't resolved, we will end our business with you. We need this sorted out by tomorrow.

Kind regards,

Amanda Kim
Operations Lead
Mills Inc
3056 Hardy Throughway
Kathleenborough, AL 60958
Phone: (856) 210-8877
EIN: 76-3789050

This email and any attachments are confidential and intended solely for the addressee.

Fazit

Am günstigsten ohne Fehler: Mistral Small 4 für 0,09 € pro 1.000 Dokumente.

  • Claude Sonnet 5 ist ebenfalls fehlerfrei, aber 40,9× teurer.

Prompt für alle Modelle

You triage the support inbox. Read the email below and return only JSON with these keys:

category        one of: billing (invoices, payments, charges), delivery (where is the order, shipping,
                address change), complaint (damaged, wrong or defective goods, warranty claims),
                technical (login, app or system errors, integrations), cancellation (cancel an order,
                contract or subscription), sales (quotes, prices, interest before buying)
priority        one of: urgent, high, normal, low (rules below)
sentiment       one of: positive, neutral, negative (the customer's tone)
customer_name   full name of the customer who wrote the request
order_number    the customer's order number, if mentioned
invoice_number  invoice number, if mentioned
amount          the amount of money the request is about (number)
currency        ISO 4217 code of that amount (USD, EUR, CZK, …)
deadline        the date by which the customer wants a resolution or answer (YYYY-MM-DD)

Priority rules:
- urgent: the customer cannot work right now, or the deadline is at most 1 day after the email date
- high: the deadline is at most 7 days after the email date, or the customer threatens to cancel
  or escalate (lawyer, ending the business)
- low: the customer says explicitly that it is not urgent
- normal: everything else

Rules:
- A thread: judge the newest message; order numbers, invoice numbers and amounts may come from the
  quoted earlier messages. A forwarded email: the customer is the original sender, not the
  colleague who forwarded it.
- Resolve relative deadlines ("by Friday", "by tomorrow", "by the end of the month") against the
  date of the message that states them.
- Support ticket numbers, tax IDs and phone numbers are not order or invoice numbers.
- If a value is not in the email, return null. Do not guess.
- Amounts as numbers with a decimal point, no thousands separators and no currency symbol.

So bewerten wir

Exakte Übereinstimmung pro Feld nach Normalisierung von Datumsangaben, Beträgen und Leerzeichen. Fehlende diakritische Zeichen zählen als Fehler. Die Kosten sind der reale Tokenverbrauch dieses Laufs, umgerechnet zum Kurs in der Fußzeile.

Was jedes Modell extrahiert hat

FeldRichtiger WertMistral Small 49 / 9 FelderGemma 4 31B9 / 9 FelderGPT-6 Luna9 / 9 FelderDeepSeek V4.1 Flash9 / 9 FelderQwen3.8 Flash9 / 9 FelderGemini 3.5 Flash Lite9 / 9 FelderMistral Medium 3.59 / 9 FelderGPT-6 Sol9 / 9 FelderGemini 3.8 Flash9 / 9 FelderClaude Sonnet 59 / 9 Felder
Kategoriecomplaintcomplaint (richtig)complaint (richtig)complaint (richtig)complaint (richtig)complaint (richtig)complaint (richtig)complaint (richtig)complaint (richtig)complaint (richtig)complaint (richtig)
Prioritäturgenturgent (richtig)urgent (richtig)urgent (richtig)urgent (richtig)urgent (richtig)urgent (richtig)urgent (richtig)urgent (richtig)urgent (richtig)urgent (richtig)
Stimmungnegativenegative (richtig)negative (richtig)negative (richtig)negative (richtig)negative (richtig)negative (richtig)negative (richtig)negative (richtig)negative (richtig)negative (richtig)
KundennameAmanda KimAmanda Kim (richtig)Amanda Kim (richtig)Amanda Kim (richtig)Amanda Kim (richtig)Amanda Kim (richtig)Amanda Kim (richtig)Amanda Kim (richtig)Amanda Kim (richtig)Amanda Kim (richtig)Amanda Kim (richtig)
BestellnummerORD-2026-3290ORD-2026-3290 (richtig)ORD-2026-3290 (richtig)ORD-2026-3290 (richtig)ORD-2026-3290 (richtig)ORD-2026-3290 (richtig)ORD-2026-3290 (richtig)ORD-2026-3290 (richtig)ORD-2026-3290 (richtig)ORD-2026-3290 (richtig)ORD-2026-3290 (richtig)
Rechnungsnummer2026-98572026-9857 (richtig)2026-9857 (richtig)2026-9857 (richtig)2026-9857 (richtig)2026-9857 (richtig)2026-9857 (richtig)2026-9857 (richtig)2026-9857 (richtig)2026-9857 (richtig)2026-9857 (richtig)
Betrag—— (richtig)— (richtig)— (richtig)— (richtig)— (richtig)— (richtig)— (richtig)— (richtig)— (richtig)— (richtig)
Währung—— (richtig)— (richtig)— (richtig)— (richtig)— (richtig)— (richtig)— (richtig)— (richtig)— (richtig)— (richtig)
Frist2026-01-302026-01-30 (richtig)2026-01-30 (richtig)2026-01-30 (richtig)2026-01-30 (richtig)2026-01-30 (richtig)2026-01-30 (richtig)2026-01-30 (richtig)2026-01-30 (richtig)2026-01-30 (richtig)2026-01-30 (richtig)
TokensEingabe / Ausgabe650 / 90679 / 88755 / 117899 / 2001.002 / 592667 / 108650 / 90755 / 99667 / 765921 / 211
davon verdecktes Nachdenkenals Ausgabe berechnet0050137482003265786
davon aus dem CacheEingabe mit Rabatt40645305867680374000
Kosten für dieses Dokumentdieser Lauf0,0001 €0,0001 €0,0001 €0,0002 €0,0003 €0,0004 €0,0015 €0,0023 €0,0031 €0,0036 €
Pro 1.000 Dokumentefür die gleiche Art von Dokument0,09 €0,12 €0,12 €0,19 €0,30 €0,43 €1,52 €2,30 €3,10 €3,64 €
Latenzdieser Lauf0,7 s3,6 s2,4 s2,5 s8,3 s0,9 s0,8 s3 s2,9 s3,8 s